© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 72189
    Prev
    Next
    INDEX
    Explanations

    technical writing snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.80
     offerts
    -0.56
    FileChooser
    -0.56
    AndEndTag
    -0.55
     Chart
    -0.52
     Shot
    -0.52
     verwijzen
    -0.50
     coûte
    -0.49
     rigue
    -0.49
     cubiertas
    -0.49
    POSITIVE LOGITS
     />";
    0.67
     متعلقه
    0.63
     out
    0.61
    __':
    0.54
    +#+#
    0.54
    ']],
    0.54
    out
    0.54
    />";
    0.53
     ExecuteAsync
    0.53
    mergeFrom
    0.52
    Activations Density 0.000%

    No Known Activations